Chrome extension

forangel2014/Probabilistic-Uncertain-Reward-Model

Python

8

4 commits

updated Oct 9, 2025

README

Probilistic Uncertain Reward Model

preparation

pip install -r requirement.txt
python setting.py --reward_model_path <your_reward_model_path> --policy_model_path <your_policy_model_path>
python scripts/process_preference.py
python scripts/process_rlhf.py

reward model training (4 GPUs)

bash run_purm.sh

RLHF with PURM (8 GPUs)

cd OpenRLHF
CUDA_VISIBLE_DEVICES=7 python reward_server.py
bash run.sh

Similar repos

PrasannS/d2po

7

fnlp/moss-rlhf-policy-model-7B-en

MOSS-RLHF

2

OpenLMLab/MOSS-RLHF

Secrets of RLHF in Large Language Models Part I: PPO

1,427

joeljang/RLPHF

Personalized Soups: Personalized Large Language Model Alignment via Post-hoc Parameter Merging

123

Ablustrund/moss-rlhf-reward-model-7B-zh

MOSS-RLHF

32

fnlp/moss-rlhf-reward-model-7B-en

MOSS-RLHF

9

SeanLeng1/Reward-Calibration

21

fnlp/moss-rlhf-sft-model-7B-en

MOSS-RLHF

2

forangel2014/Probabilistic-Uncertain-Reward-Model

Python

8

4 commits

updated Oct 9, 2025

README

Probilistic Uncertain Reward Model

preparation

pip install -r requirement.txt
python setting.py --reward_model_path <your_reward_model_path> --policy_model_path <your_policy_model_path>
python scripts/process_preference.py
python scripts/process_rlhf.py

reward model training (4 GPUs)

bash run_purm.sh

RLHF with PURM (8 GPUs)

cd OpenRLHF
CUDA_VISIBLE_DEVICES=7 python reward_server.py
bash run.sh

Similar repos

PrasannS/d2po

7

fnlp/moss-rlhf-policy-model-7B-en

MOSS-RLHF

2

OpenLMLab/MOSS-RLHF

Secrets of RLHF in Large Language Models Part I: PPO

1,427

joeljang/RLPHF

Personalized Soups: Personalized Large Language Model Alignment via Post-hoc Parameter Merging

123

Ablustrund/moss-rlhf-reward-model-7B-zh

MOSS-RLHF

32

fnlp/moss-rlhf-reward-model-7B-en

MOSS-RLHF

9

SeanLeng1/Reward-Calibration

21

fnlp/moss-rlhf-sft-model-7B-en

MOSS-RLHF

2